Just released v1.5.0 with IBM watsonx integration.

  ```python
  # Works with any provider now
  client = LLMClient(provider="watsonx")
  client = LLMClient(provider="anthropic")
  client = LLMClient(provider="openai")

  response = client.query("Analyze this data")

  New in v1.5.0:
  - IBM watsonx provider with Granite models
  - Same API across all 5 providers
  - Auto-fallback still works
  - Enterprise authentication

  Also supports 100+ local Ollama models including OpenAI's new GPT-OSS.